IBM Works To Make Traffic Smarter And Smoother

What exactly is IBM, these days? Since dropping the ThinkPad line off at the doorstep of Lenovo, the company has strayed from the consumer realm. These days, they're focusing mostly on services and enterprise, not to mention a little thing by the name of Watson. But the company has made sure to make one thing very clear: they're out to make a smarter planet. And smarter means safer. IBM has joined with Caltrans and UC Berkeley in order to help commuters avoid congested roadways.

The collaborative effort aims to help people avoid congestion before they get to it, and to better understand, predict and manage traffic flow. The highlight is a new predictive modeling tool that will let drivers quickly access personalized travel recommendations to help them avoid congestion, and save time and fuel. By joining forces, IBM, Caltrans and the Mobile Millennium team within the CCIT hope to provide drivers with valuable predictive information on what traffic patterns are likely to look like – even before they leave work or home and get in their vehicles – rather than discover what has already happened and is being reported.

Using this predictive and analytic traffic tool, transportation agencies and city planners in the future will be able to proactively design, manage and optimize transportation systems to deal with ever-increasing traffic due to population growth and increasing urbanization. It's hard to say if something like this really will help places like LA iron out gridlock problems, but the video here definitely gives us hope that traffic jams will at least partially be a thing of the past.

Via:  IBM
rapid1 3 years ago

Traffic is to variable and live for this to ever work. If it starts routing around a traffic jam on an interstate 30 minutes prior there will be a wreck on one of it's side routes in 45 seconds, so by the time you get to your car in the parking lot there will be a new route, and the same will be true 45sec to 1:30min's after that, but after you have already started on it. Unless they had "smart cars" that automatically change routes on the fly there would be no way to make this work. The big thing about that is there are only so many routes to take, say 4 to 10 from one area to one specific location. With growing population in a city the variables just don't fit as you have more individuals or active cars but still the same amount of routes. As I said traffic is instant so the farther out you predict the worse that prediction will be unless you have a live routing function with roads that can automatically clear an accident, and make people stop slowing down to look at said accident, traffic stop, 2 hot women jogging, building on fire etc etc. There is no way to predict real time flow of said traffic on whatever number of routes there are available in whatever city at that certain time.

specjre 3 years ago

I don't think they are focusing so much on wrecks. Those are of course very unpredictable, but they can analyze when roads get congested and make decisions based on that information. As far as wrecks go I think they can be avoided somewhat. I think the focus would have to be letting people know about 30minute+ delays instead of "this wreck just happened stay away". When there isn't normally bad traffic and a wreck is what causes it, it takes a little bit of time for it to build up.

omegadraco 3 years ago

We will have smart cars that drive themselves soon. I would enjoy my commute so much more if I did not have to drive.

HHGrrl 3 years ago

GPS manufacturers already offer traffic services. Wonder how they compare to what IBM is doing?

Post a Comment
or Register to comment